{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N3IDXNM7TYBCPPQIQQMYEYQ4YI","short_pith_number":"pith:N3IDXNM7","canonical_record":{"source":{"id":"2405.15074","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-05-23T21:50:54Z","cross_cats_sorted":["cs.LG","math.OC","math.PR","math.ST","stat.TH"],"title_canon_sha256":"23e4b19de055bc9f89621367eeb257c781d803a522879661347bca5a5de20c93","abstract_canon_sha256":"d80a48d91e9915a4aac8a3c43770de105b2da0a8dbe5d50aa05033269c82e476"},"schema_version":"1.0"},"canonical_sha256":"6ed03bb59f9e0227be08841982621cc20fae27b3cdc3a8debde207d90b816919","source":{"kind":"arxiv","id":"2405.15074","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15074","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15074v3","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15074","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"pith_short_12","alias_value":"N3IDXNM7TYBC","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"pith_short_16","alias_value":"N3IDXNM7TYBCPPQI","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"pith_short_8","alias_value":"N3IDXNM7","created_at":"2026-07-05T10:51:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N3IDXNM7TYBCPPQIQQMYEYQ4YI","target":"record","payload":{"canonical_record":{"source":{"id":"2405.15074","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-05-23T21:50:54Z","cross_cats_sorted":["cs.LG","math.OC","math.PR","math.ST","stat.TH"],"title_canon_sha256":"23e4b19de055bc9f89621367eeb257c781d803a522879661347bca5a5de20c93","abstract_canon_sha256":"d80a48d91e9915a4aac8a3c43770de105b2da0a8dbe5d50aa05033269c82e476"},"schema_version":"1.0"},"canonical_sha256":"6ed03bb59f9e0227be08841982621cc20fae27b3cdc3a8debde207d90b816919","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:03.664848Z","signature_b64":"HrhTMF4igSJcN0qFHfShIudSGPfoHAgcIoJFOHErRfiaOcPyWsMqtwGQ5GOtYlZSQaev1loIYGW+vkU2rbC+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ed03bb59f9e0227be08841982621cc20fae27b3cdc3a8debde207d90b816919","last_reissued_at":"2026-07-05T10:51:03.664345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:03.664345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.15074","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:51:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jYFh7q6mNeBLpxjjyqsOftaU4rRDCMaSmvWYbnJL5VluQJZzEu8elUTjm6S0FAu+LBkNBefPjhelyw/b05XFDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:52:39.184842Z"},"content_sha256":"7b6c57dbed7f3e4d645ae5ca00e4dc9c6584fb085aa6f4a78fe2ddccb350d4b0","schema_version":"1.0","event_id":"sha256:7b6c57dbed7f3e4d645ae5ca00e4dc9c6584fb085aa6f4a78fe2ddccb350d4b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N3IDXNM7TYBCPPQIQQMYEYQ4YI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"4+3 Phases of Compute-Optimal Neural Scaling Laws","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","math.PR","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Courtney Paquette, Elliot Paquette, Jeffrey Pennington, Lechao Xiao","submitted_at":"2024-05-23T21:50:54Z","abstract_excerpt":"We consider the solvable neural scaling model with three parameters: data complexity, target complexity, and model-parameter-count. We use this neural scaling model to derive new predictions about the compute-limited, infinite-data scaling law regime. To train the neural scaling model, we run one-pass stochastic gradient descent on a mean-squared loss. We derive a representation of the loss curves which holds over all iteration counts and improves in accuracy as the model parameter count grows. We then analyze the compute-optimal model-parameter-count, and identify 4 phases (+3 subphases) in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15074","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.15074/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:51:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3/bF861+5MdoVzme5CTmD/RViA/ZIFRV6fYHGDH3QyLPthNaaCPHpu70FugrhORsfr2hO1A/tfVUq1ocWa0pCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:52:39.185813Z"},"content_sha256":"732bc73b41598a6155fdd6526e4c1869d43e18124680a3d1c9387b2137580ca6","schema_version":"1.0","event_id":"sha256:732bc73b41598a6155fdd6526e4c1869d43e18124680a3d1c9387b2137580ca6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N3IDXNM7TYBCPPQIQQMYEYQ4YI/bundle.json","state_url":"https://pith.science/pith/N3IDXNM7TYBCPPQIQQMYEYQ4YI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N3IDXNM7TYBCPPQIQQMYEYQ4YI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T08:52:39Z","links":{"resolver":"https://pith.science/pith/N3IDXNM7TYBCPPQIQQMYEYQ4YI","bundle":"https://pith.science/pith/N3IDXNM7TYBCPPQIQQMYEYQ4YI/bundle.json","state":"https://pith.science/pith/N3IDXNM7TYBCPPQIQQMYEYQ4YI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N3IDXNM7TYBCPPQIQQMYEYQ4YI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N3IDXNM7TYBCPPQIQQMYEYQ4YI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d80a48d91e9915a4aac8a3c43770de105b2da0a8dbe5d50aa05033269c82e476","cross_cats_sorted":["cs.LG","math.OC","math.PR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-05-23T21:50:54Z","title_canon_sha256":"23e4b19de055bc9f89621367eeb257c781d803a522879661347bca5a5de20c93"},"schema_version":"1.0","source":{"id":"2405.15074","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15074","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15074v3","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15074","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"pith_short_12","alias_value":"N3IDXNM7TYBC","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"pith_short_16","alias_value":"N3IDXNM7TYBCPPQI","created_at":"2026-07-05T10:51:03Z"},{"alias_kind":"pith_short_8","alias_value":"N3IDXNM7","created_at":"2026-07-05T10:51:03Z"}],"graph_snapshots":[{"event_id":"sha256:732bc73b41598a6155fdd6526e4c1869d43e18124680a3d1c9387b2137580ca6","target":"graph","created_at":"2026-07-05T10:51:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.15074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the solvable neural scaling model with three parameters: data complexity, target complexity, and model-parameter-count. We use this neural scaling model to derive new predictions about the compute-limited, infinite-data scaling law regime. To train the neural scaling model, we run one-pass stochastic gradient descent on a mean-squared loss. We derive a representation of the loss curves which holds over all iteration counts and improves in accuracy as the model parameter count grows. We then analyze the compute-optimal model-parameter-count, and identify 4 phases (+3 subphases) in t","authors_text":"Courtney Paquette, Elliot Paquette, Jeffrey Pennington, Lechao Xiao","cross_cats":["cs.LG","math.OC","math.PR","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-05-23T21:50:54Z","title":"4+3 Phases of Compute-Optimal Neural Scaling Laws"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15074","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7b6c57dbed7f3e4d645ae5ca00e4dc9c6584fb085aa6f4a78fe2ddccb350d4b0","target":"record","created_at":"2026-07-05T10:51:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d80a48d91e9915a4aac8a3c43770de105b2da0a8dbe5d50aa05033269c82e476","cross_cats_sorted":["cs.LG","math.OC","math.PR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-05-23T21:50:54Z","title_canon_sha256":"23e4b19de055bc9f89621367eeb257c781d803a522879661347bca5a5de20c93"},"schema_version":"1.0","source":{"id":"2405.15074","kind":"arxiv","version":3}},"canonical_sha256":"6ed03bb59f9e0227be08841982621cc20fae27b3cdc3a8debde207d90b816919","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ed03bb59f9e0227be08841982621cc20fae27b3cdc3a8debde207d90b816919","first_computed_at":"2026-07-05T10:51:03.664345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:03.664345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HrhTMF4igSJcN0qFHfShIudSGPfoHAgcIoJFOHErRfiaOcPyWsMqtwGQ5GOtYlZSQaev1loIYGW+vkU2rbC+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:03.664848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15074","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b6c57dbed7f3e4d645ae5ca00e4dc9c6584fb085aa6f4a78fe2ddccb350d4b0","sha256:732bc73b41598a6155fdd6526e4c1869d43e18124680a3d1c9387b2137580ca6"],"state_sha256":"f70809f90266d828222bfe12176d2f82274ccf6acf640df9a5568c8b4d53d82d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X42qdvuZvdjsCpZFRaSN4fEOTLO42/ke6cVRK7Qa8y9UgwXD6RK2SQy+o7ST9ui3Z71lSOc9fx/BEzKInk9uDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:52:39.192962Z","bundle_sha256":"c0c33b3f0f289d0c93a6318fcd5524d1435c45f8cbc0c1e6c90106dc6f16404a"}}